For the best experience browsing on ITS Australia, we recommend using the latest version of Chrome, Firefox, Safari or Edge. The ITS website also runs on mobile web browsers.
You can download supported browsers using one of these links:
To check what browser version you are using, visit What Is My Browser.
ITS Australia's ITS Tech Talk series is transport technology 101. Each episode will serve as an introduction to one key part of the ITS industry . . . this is episode 4.
An Artificial Intelligence (AI) driven road safety network aims to make Australian roads safer, reduce congestion, save lives and save money. Register for this, and all of our upcoming ITS Tech Talks, through the ITS Australia Portal.
Dr Chen Cai Senior Manager / Ernst & Young Senior Manager / Ernst & Young
Dr Cai is a senior manager at EY, working towards accelerating the adoption of AI and digital twin in transformational industries. He obtained a PhD in Transport at University College London, began his research career at National ICT Australia (NICTA), moved to CSIRO as NICTA was merged with CSIRO to form Data61, where he founded the Transport Analytics group.
The group was the recipient of numerous awards: NSW Premier’s Innovation Initiative, Committee for Sydney Award, iAward, CSIRO Collaboration Medal, and Intelligent Transport Systems (ITS) Australia Awards. The core of group followed him to join EY in June 2022. He was an elected board director of ITS Australia from 2017 to 2021.
Get in touch with Data61 CSIRO.
a. The current pandemic has profoundly changed the way we work and live. Some of the changes are likely to be permanent, e.g. increased working from home. Such long-term changes can be captured by data and learnt by ML algorithms.
b. ML algorithms may still struggle to predict the impact of another extraordinary event (of adverse impact), due to the varying nature of such events and limited samples.
c. Investigations are being made to combine ML with granular simulation engines for the modelling of impact from major events. For example, ML for predicting human behaviour and simulation engine to model the interaction of human with environment.
Yes, it is possible. In this case the AV can rely on its own perception from cameras or a GPS navigation system or combined.
Yes. The intention is to provide labelled data samples to the physically measured events (excitation readings on the accelerometers).
a. If we know how ML algorithms works, like in image processing, then we can artificially perturb the input and defeat the algorithm.
b. Generally, by going through the training phase of ML algorithms, we would be able to use measures like precision and recall to gauge the likelihood for incorrect interpretation.
Membership of ITS Australia offers a range of benefits